Anthropic: Claude Opus 4.8 vs Inception: Mercury 2
Summary
Claude Opus 4.8 (low) vs Mercury 2 (medium) benchmark comparison: Claude Opus 4.8 (low) leads on average score with 7.7 vs 7.5. Mercury 2 (medium) has the lower benchmark cost at $0.058 vs $1.270. Mercury 2 (medium) is faster at 2.24s vs 10.83s, with pass rates of 79.4% vs 54.0%.
Recommended model: Mercury 2 (medium) - Its score stays close to the best score here (7.5 vs 7.7), while costing about 22.0x less than Claude Opus 4.8 (low).
7.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#45
#56
Reliability
10.0First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
10.0First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
8.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 4Extra formatting: 1No answer: 1Response Time (avg)10.83sResponse Time (max)127.97sResponse Time (total)227.39sA test is fully passed only if every run passed for that test.…
A test is fully passed only if every run passed for that test.Wrong answer: 8Did not follow instructions: 3Response Time (avg)2.24sResponse Time (max)14.63sResponse Time (total)44.72sA test is fully passed only if every run passed for that test.…
Attempt pass rate
79.4%Attempt pass rate = passed attempts / total attempts across runs.…
54.0%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
63Total Runs…
63Total Runs…
Cost per result
8.466Shows the average cost per correct benchmark answer in cents (lower is better).…
0.578Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$1.270Total Cost (Current Price)…
$0.058Total Cost (Current Price)…
Input Price
$5.000 / 1MInput Price…
$0.250 / 1MInput Price…
Output Price
$25.000 / 1MOutput Price…
$0.750 / 1MOutput Price…
Total Input Tokens
60,946Total Input Tokens…
35,116Total Input Tokens…
Output Tokens
31,771Output Tokens…
4,048Output Tokens…
Reasoning Tokens
6,831Reasoning Tokens…
61,219Reasoning Tokens…
Response Time (avg)
10.83sResponse Time (avg)…
2.24sResponse Time (avg)…
Response Time (max)
127.97sResponse Time (max)…
14.63sResponse Time (max)…
Response Time (total)
227.39sResponse Time (total)…
44.72sResponse Time (total)…
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.30sResponse Time (max)4.34sResponse Time (total)13.18sA test is fully passed only if every run passed for that test.…
6.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
50.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Wrong answer: 1Response Time (avg)1.12sResponse Time (max)2.46sResponse Time (total)4.49sA test is fully passed only if every run passed for that test.…
6.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.6Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
77.8%Attempt pass rate = passed attempts / total attempts across runs.…
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Extra formatting: 1Wrong answer: 1Response Time (avg)7.58sResponse Time (max)12.19sResponse Time (total)22.74sA test is fully passed only if every run passed for that test.…
8.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
77.8%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.04sResponse Time (max)3.06sResponse Time (total)6.11sA test is fully passed only if every run passed for that test.…
9.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)20.84sResponse Time (max)20.84sResponse Time (total)20.84sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.28sResponse Time (max)3.28sResponse Time (total)3.28sA test is fully passed only if every run passed for that test.…
6.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
66.7%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.27sResponse Time (max)2.50sResponse Time (total)4.54sA test is fully passed only if every run passed for that test.…
7.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
83.3%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.11sResponse Time (max)1.47sResponse Time (total)2.21sA test is fully passed only if every run passed for that test.…
5.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)45.53sResponse Time (max)127.97sResponse Time (total)136.60sA test is fully passed only if every run passed for that test.…
2.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
11.1%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)6.48sResponse Time (max)14.63sResponse Time (total)19.43sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.55sResponse Time (max)2.55sResponse Time (total)2.55sA test is fully passed only if every run passed for that test.…
4.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)821msResponse Time (max)821msResponse Time (total)821msA test is fully passed only if every run passed for that test.…
9.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.78sResponse Time (max)3.78sResponse Time (total)5.56sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.07sResponse Time (max)1.07sResponse Time (total)1.07sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.01sResponse Time (max)3.31sResponse Time (total)9.04sA test is fully passed only if every run passed for that test.…
5.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Wrong answer: 1Response Time (avg)949msResponse Time (max)1.18sResponse Time (total)2.85sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.85sResponse Time (max)6.85sResponse Time (total)6.85sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.89sResponse Time (max)1.89sResponse Time (total)1.89sA test is fully passed only if every run passed for that test.…
3.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)5.48sResponse Time (max)5.48sResponse Time (total)5.48sA test is fully passed only if every run passed for that test.…
3.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.58sResponse Time (max)2.58sResponse Time (total)2.58sA test is fully passed only if every run passed for that test.…